EpistemeAI/Reasoning-Medical0.1-E4B-sft-Q8_0
Quantization (fewer layers) vs EpistemeAI/Reasoning-Medical0.1-E4B-sft. EpistemeAI/Reasoning-Medical0.1-E4B-sft-Q8_0 matches part of EpistemeAI/Reasoning-Medical0.1-E4B-sft (677 of its 2130 tensors; the rest of EpistemeAI/Reasoning-Medical0.1-E4B-sft has no counterpart). On the shared part: EpistemeAI/Reasoning-Medical0.1-E4B-sft-Q8_0 is a GGUF quantization (Q8_0) of the same weights: 297 tensors match exactly and 380 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168